All stories

1 outlets · filed 27 October 2026

Google’s Genie 4 world model adds audio, more realistic worlds, and real-time steering

This story is from the archive. It was covered between 27 October 2026 and 27 October 2026, and nothing below has been updated since. See what is happening now.

Genie 4 can maintain a consistent scene for up to two minutes, double Genie 3's limit, and offers better physics and more humanlike characters.

What the coverage shows

Both The Verge and TechCrunch center Google’s Genie 4 world model and overlap on the same three upgrades: more realistic worlds, audio generation, and real-time prompting or steering during a simulation. The Verge adds that Google says the model also uses Gemini 3.8, which TechCrunch does not mention, while TechCrunch alone notes it is in research preview for trusted testers.

Written by Crossfiled from the 1 headlines and extracts below, not from the articles themselves. It describes how the outlets framed this, not what happened. Open any headline for a summary of that article.

TechCrunch

How it broke

In this story

1outlets
0videos
1articles

More on Tech & AI

Every Tech & AI story, across every outlet